{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FEM25YDZJJAHV55MLLTA2Q3YRI","short_pith_number":"pith:FEM25YDZ","schema_version":"1.0","canonical_sha256":"2919aee0794a407af7ac5ae60d43788a0cced6f4f6911bdc4f73b3eac44944a6","source":{"kind":"arxiv","id":"2502.10631","version":1},"attestation_state":"computed","paper":{"title":"ControllableGPT: A Ground-Up Designed Controllable GPT for Molecule Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Bo Li, Rick Stevens, Songhao Jiang, Xuefeng Liu","submitted_at":"2025-02-15T01:49:35Z","abstract_excerpt":"Large Language Models (LLMs) employ three popular training approaches: Masked Language Models (MLM), Causal Language Models (CLM), and Sequence-to-Sequence Models (seq2seq). However, each approach has its strengths and limitations, and faces challenges in addressing specific tasks that require controllable and bidirectional generation, such as drug optimization. To address this challenge, inspired by the biological processes of growth and evolution, which involve the expansion, shrinking, and mutation of sequences, we introduce ControllableGPT. This initiative represents the first effort to co"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.10631","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-15T01:49:35Z","cross_cats_sorted":["cs.AI","q-bio.BM"],"title_canon_sha256":"9e6dd90127d4fa421983f625eab13310421cf0ce40093a92838bcb93750d0cc4","abstract_canon_sha256":"ab361955951c6ed7f293e3d121130a7c737f507770c373ba70ae5e7555936ce0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:55.542063Z","signature_b64":"EOaBQPFfswBbioqNQ5scugoT784OhazsGIKa/JtH7n0TG751Y3BxHUkPCOFW6LaqnPc94B+Jjks07JCbx2sRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2919aee0794a407af7ac5ae60d43788a0cced6f4f6911bdc4f73b3eac44944a6","last_reissued_at":"2026-07-05T10:14:55.541557Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:55.541557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ControllableGPT: A Ground-Up Designed Controllable GPT for Molecule Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Bo Li, Rick Stevens, Songhao Jiang, Xuefeng Liu","submitted_at":"2025-02-15T01:49:35Z","abstract_excerpt":"Large Language Models (LLMs) employ three popular training approaches: Masked Language Models (MLM), Causal Language Models (CLM), and Sequence-to-Sequence Models (seq2seq). However, each approach has its strengths and limitations, and faces challenges in addressing specific tasks that require controllable and bidirectional generation, such as drug optimization. To address this challenge, inspired by the biological processes of growth and evolution, which involve the expansion, shrinking, and mutation of sequences, we introduce ControllableGPT. This initiative represents the first effort to co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10631","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.10631/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.10631","created_at":"2026-07-05T10:14:55.541626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10631v1","created_at":"2026-07-05T10:14:55.541626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10631","created_at":"2026-07-05T10:14:55.541626+00:00"},{"alias_kind":"pith_short_12","alias_value":"FEM25YDZJJAH","created_at":"2026-07-05T10:14:55.541626+00:00"},{"alias_kind":"pith_short_16","alias_value":"FEM25YDZJJAHV55M","created_at":"2026-07-05T10:14:55.541626+00:00"},{"alias_kind":"pith_short_8","alias_value":"FEM25YDZ","created_at":"2026-07-05T10:14:55.541626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23061","citing_title":"C-MORAL: Controllable Multi-Objective Molecular Optimization with Reinforcement Alignment for LLMs","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FEM25YDZJJAHV55MLLTA2Q3YRI","json":"https://pith.science/pith/FEM25YDZJJAHV55MLLTA2Q3YRI.json","graph_json":"https://pith.science/api/pith-number/FEM25YDZJJAHV55MLLTA2Q3YRI/graph.json","events_json":"https://pith.science/api/pith-number/FEM25YDZJJAHV55MLLTA2Q3YRI/events.json","paper":"https://pith.science/paper/FEM25YDZ"},"agent_actions":{"view_html":"https://pith.science/pith/FEM25YDZJJAHV55MLLTA2Q3YRI","download_json":"https://pith.science/pith/FEM25YDZJJAHV55MLLTA2Q3YRI.json","view_paper":"https://pith.science/paper/FEM25YDZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10631&json=true","fetch_graph":"https://pith.science/api/pith-number/FEM25YDZJJAHV55MLLTA2Q3YRI/graph.json","fetch_events":"https://pith.science/api/pith-number/FEM25YDZJJAHV55MLLTA2Q3YRI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FEM25YDZJJAHV55MLLTA2Q3YRI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FEM25YDZJJAHV55MLLTA2Q3YRI/action/storage_attestation","attest_author":"https://pith.science/pith/FEM25YDZJJAHV55MLLTA2Q3YRI/action/author_attestation","sign_citation":"https://pith.science/pith/FEM25YDZJJAHV55MLLTA2Q3YRI/action/citation_signature","submit_replication":"https://pith.science/pith/FEM25YDZJJAHV55MLLTA2Q3YRI/action/replication_record"}},"created_at":"2026-07-05T10:14:55.541626+00:00","updated_at":"2026-07-05T10:14:55.541626+00:00"}